Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Video Stabilization on YouTube

googleresearch.blogspot.in

Post reply on HN
Print view View original

21–30 of 51 posts

Re: Video Stabilization on YouTube

#21

Post by drewyeaton »

ajb wrote: post #18

Seems to work well- I just tried it on a tiger cub vid, which I've had for years and was taken with an el-cheapo digital camera: Shaky version: http://youtu.be/g5P9WwHdOSI Stabilised version http://youtu.be/wXfbRUk_1Bg There is some motion blur (around 24 seconds, when the momma tiger lies down) which is a bit puzzling once the image has been stabilised. But hey, it's better than it was before.

The motion blur was there in the first place, you just don't notice it because there's also _motion_. When you remove the motion (shaking, jerking the camera), you're left with just the blur.

Re: Video Stabilization on YouTube

#23

Post by objclxt »

Pelayo wrote: post #9

They should apply this during movie fighting scenes. Then we might actually see the fight instead of the blur caused by "exciting cameras".

Going off on a tangent here, but from the distant memory of my film studies degree days one of the reasons you get so much fast cutting and hard-to-make-out action in modern fight scenes is because choreographing and shooting a fight scene properly is hard work, particularly if your actors aren't that experienced in stage combat. It's a big cheat, designed to make shooting fight scenes much easier (this is especially true if you're shooting a fight-scene where one participant is CG'd in).

Re: Video Stabilization on YouTube

#25

Post by hmottestad »

vasco wrote: post #3

I really hope this keeps being optional because otherwise a lot of the authentic value of the videos will be lost. Also, the demo they showed looked like it was algorithmically deteriorated to make the change more noticeable. There's shaky hands and then there's parkinsons-level shaking which was what the demo showed...

If they used a telephoto lens then the shaking would be much more noticeable. Also the motion hints at someone actually attempting to correct for the movements, but because it's zoomed so far in every movement to counteract the shaking is greatly magnified.

Re: Video Stabilization on YouTube

#26

Post by ajb »

drewyeaton wrote: post #21
ajb wrote: post #18

Seems to work well- I just tried it on a tiger cub vid, which I've had for years and was taken with an el-cheapo digital camera: Shaky version: http://youtu.be/g5P9WwHdOSI Stabilised version http://youtu.be/wXfbRUk_1Bg There is some motion blur (around 24 seconds, when the momma tiger lies down) which is a bit puzzling once the image has been stabilised. But hey, it's better than it was before.

The motion blur was there in the first place, you just don't notice it because there's also _motion_. When you remove the motion (shaking, jerking the camera), you're left with just the blur.

Yes, I know. But the viewer won't know that, because they don't know where the motion was before it was stabilised.

Re: Video Stabilization on YouTube

#27

Post by hedgehog »

MrMike wrote: post #22
hamoid wrote: post #15

I wonder when will we get this quality http://pages.cs.wisc.edu/~fliu/project/3dstab.htm

This is amazing. Wonder if there is a commercial implementation yet?

These guys do some pretty amazing stuff, video stabilization is one of the applications: http://www.2d3.com/

Re: Video Stabilization on YouTube

#28

Post by platz »

agumonkey wrote: post #14
leviathan wrote: post #11

Earlier quoted context omitted.

If you look carefully, the shakes appear too uniform to be a person shaking the camera. It looks like the camera always "shakes" in a circular motion around the center of the original camera location.

Probably a staged setup, inducing a regular shaking pattern, but I think generating rolling shutter algorithmicly would be a stretch for them, so I call physical but maybe voluntary shake.

Or maybe it's due to the 'rolling' shutter causing shear stretching as mentioned in the article

Re: Video Stabilization on YouTube

#29

Post by kami8845 »

agumonkey wrote: post #14
leviathan wrote: post #11

Earlier quoted context omitted.

If you look carefully, the shakes appear too uniform to be a person shaking the camera. It looks like the camera always "shakes" in a circular motion around the center of the original camera location.

Probably a staged setup, inducing a regular shaking pattern, but I think generating rolling shutter algorithmicly would be a stretch for them, so I call physical but maybe voluntary shake.

it's much easier to record it without much shake and then maximize the effect of their algorithm after the fact instead of recording a bunch of versions with varying degrees of shake. They completely overdid it in my opinion, the example doesn't seem authentic at all to me (though the technology remains cool)

Re: Video Stabilization on YouTube

#30

Post by CoffeeAndCoffee »

ajb wrote: post #18

Seems to work well- I just tried it on a tiger cub vid, which I've had for years and was taken with an el-cheapo digital camera: Shaky version: http://youtu.be/g5P9WwHdOSI Stabilised version http://youtu.be/wXfbRUk_1Bg There is some motion blur (around 24 seconds, when the momma tiger lies down) which is a bit puzzling once the image has been stabilised. But hey, it's better than it was before.

It also looks like the stabilized video is magnified a little bit. Regardless, these tools are really neat and they are still in their infancy. It's good to see that GooTube still believes in user-generated content.
Post reply on HN